Machine Performance Research Articles

Effect of Soil Texture on Agricultural Machine Performance in Sylhet, Bangladesh.

Soil texture is one of the primary soil physical properties that largely affects agricultural machine performance. Before implementing an agricultural machine at the farm level, it is important to test the machine to gain an understanding of its technical functionality and economic viability to get the best output from it. The research was carried out to assess how soil texture influences the performance of machinery, aiming to determine the effectiveness of agricultural equipment on a particular type of land. Soil samples were collected from nine different fields, and their textures were determined using hydrometer analysis. To correlate soil textural classes with machine performance, machinery data—effective field capacity, forward speed, and field efficiency—were calculated by operating a combine harvester on the study areas during the harvesting season of Boro rice. Two types of soil were identified: loamy sand and sandy loam. The findings of the study showed that machine efficiency has a positive correlation with sand proportion and a negative correlation with clay and silt fractions. It was observed that soil with loamy sand-type textural classes demonstrated better field efficiency, higher effective field capacity, and higher forward speed compared to sandy loam soil. Small and irregularly shaped fields also caused variation in performance. The study identified significant variation in speed between these two types of soils but no significant effect on effective field capacity or field efficiency at the 5% level of significance. The outcomes of this research will help farmers make informed decisions when selecting appropriate equipment for their agricultural operations.

An experimental validation of diffusion-based devolatilization models in extruders using post-industrial and post-consumer plastic waste

Abstract Extrusion is a key process in mechanical recycling. In a degassing step, volatile components, including all impurities and moisture, are removed from a polymer melt to ensure consistently high quality of the recyclates. Predicting devolatilization performance is therefore of interest in the design of degassing screws; in the plastics industry, it also plays an important role in the transition from a linear to a circular economy. Using two different devolatilization models, we first modelled the degassing process of a lab-scale twin-screw extruder and an industrial-scale recycling single-screw extruder. We then predicted the devolatilization performance of both machines, validated the results with experimental data obtained from emissions tests carried out with post-industrial and post-consumer polypropylene materials and performed linear regression analysis to compare our two models in terms of predictive quality. Our results showed that both models are equally suitable for reliable prediction of the devolatilization performance.

Comparative analysis of machine learning algorithms for Alzheimer's disease classification using EEG signals and genetic information

Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, memory impairments, and behavioral changes. The presence of abnormal beta-amyloid plaques and tau protein tangles in the brain is known to be associated with AD. However, current limitations of imaging technology hinder the direct detection of these substances. Consequently, researchers are exploring alternative approaches, such as indirect assessments involving monitoring brain signals, cognitive decline levels, and blood biomarkers. Recent studies have highlighted the potential of integrating genetic information into these approaches to enhance early detection and diagnosis, offering a more comprehensive understanding of AD pathology beyond the constraints of existing imaging methods. Our study utilized electroencephalography (EEG) signals, genotypes, and polygenic risk scores (PRSs) as features for machine learning models. We compared the performance of gradient boosting (XGB), random forest (RF), and support vector machine (SVM) to determine the optimal model. Statistical analysis revealed significant correlations between EEG signals and clinical manifestations, demonstrating the ability to distinguish the complexity of AD from other diseases by using genetic information. By integrating EEG with genetic data in an SVM model, we achieved exceptional classification performance, with an accuracy of 0.920 and an area under the curve of 0.916. This study presents a novel approach of utilizing real-time EEG data and genetic background information for multimodal machine learning. The experimental results validate the effectiveness of this concept, providing deeper insights into the actual condition of patients with AD and overcoming the limitations associated with single-oriented data.

Design and shape optimization of interior permanent magnet synchronous machine based on hybrid cores

By designing stator teeth using grain-oriented sheets (GO) and other parts still with non-grain-oriented sheets (NGO), the electromagnetic performance of the interior permanent magnet synchronous machine (GO-IPMSM) can be improved greatly. As the stator core of the designed GO-IPMSM is a hybrid core that is composed of two different silicon sheets, both the electromagnetic and mechanical performances are affected by the stator joint shape between GO and NGO sheets. Meanwhile, with the adoption of GO, the torque ripple of GO-IPMSM is increased though the average torque is increased as well. For reducing the torque ripple, optimizing the rotor barrier shape is an effective way. In this paper, the piecewise linear interpolation method is employed for establishing the stator joint shape between GO and NGO sheets, and the polynomial method is proposed to establish the rotor barrier shape. Through the analysis, it can be seen that the stator joint shape plays a strong role in affecting the mechanical performance of the GO-IPMSM, while the effect on the electromagnetic performance is weak. The genetic algorithm is used to optimize the rotor barrier shape for achieving high average torque and low torque ripple. Lastly, a quick and accurate efficiency map calculation method based on the Kriging model is proposed for GO-IPMSM with less finite element method (FEM) samples are required.

Performance Evaluation of Some Selected Classification Algorithms in a Facial Recognition System

Facial Recognition (FR) has been an active area of research and has diverse applicable environment, it continues to be a challenging research topic. With the development of image processing and pattern recognition technology, there are many challenges in machine learning to select the appropriate classification algorithms, most especially in the area of classification of extracted features to have low classification time, high sensitivity and accuracy of the classification algorithms, so it is very important to explore the performance of different algorithms in image classification. The three selected supervised learning classification algorithms: Learning Vector Quantization (LVQ), Relevance Vector Machine (RVM), and Support Vector Machine (SVM) performance were evaluated so as to know the most effective out of the selected algorithms for facial images classification. The development of the system has four stages, the first stage is image acquisition and 180 images were taken by digital camera under same illumination and light colour background. The second stage is pre-processing to improve the images data by suppressing unwilling distortion; grayscale and normalization were used for image pre-processing. The third stage is feature extraction; Discrete Cosine Transform (DCT) is adopted for this purpose. While the fourth stage is face recognition classification, Receiver Operating Characteristics (ROC) was used to test the performance of each the three algorithms. However the Learning Vector Quantization algorithm, Relevance Vector Machine and Support Vector Machine performance have not been compared together to the most effective out of the three algorithms in term of False Positive Rate, Sensitivity, Specificity, Precision, Accuracy and Computation Time. Hence, this work evaluated the performance of the Learning Vector Quantization; Relevance Vector Machine and Support Vector Machine classification algorithms in facial recognition system and Support Vector Machine outwit the other two algorithms in facial recognition in term of specificity, recognition time and recognition accuracy at different threshold.

Faster Evaluation of Dimensional Machine Performance in Additive Manufacturing by Using COMPAQT Parts

Knowing the tolerance interval capabilities (TICs) of a manufacturing process is of prime interest, especially if specifications link the manufacturer to a customer. These TICs can be determined using the machine performance concept of ISO 22514. However, few works have applied this to Additive Manufacturing printers, while testing most of the printing area as recommended takes a very long time (nearly 1 month is common). This paper, by proposing a novel part design called COMPAQT (Component for Machine Performances Assessment in Quick Time), aims at giving the same level of printing area coverage, while keeping the manufacturing time below 24 h. The method was successfully tested on a material extrusion printer. It allowed the determination of potential and real machine tolerance interval capabilities. Independently of the feature size, those aligned with the X axis achieved lower TICs than those aligned with the Y axis, while the Z axis exhibited the best performance. The measurements specific to one part exhibited a systematic error centered around 0 mm ± 0.050 mm, while those involving two parts reached up to 0.314 mm of deviation. COMPAQT can be used in two applications: evaluating printer tolerance interval capabilities and tracking its long-term performance by incorporating it into batches of other parts.

Development of Random Forest Model for Stroke Prediction

Stroke is a significant cause of mortality and morbidity worldwide, and early detection and prevention of stroke are essential for improving patient outcomes. Machine learning algorithms have been used in recent years to predict the risk of stroke by leveraging large amounts of clinical and demographic data. The development of a stroke prediction system using Random Forest machine learning algorithm is the main objective of this thesis. The primary goal of the project is to increase the accuracy of stroke detection while addressing the shortcomings of the current system, which include real- time deployment and interpretability issues with logistic regression. The development and use of an ensemble machine learning-based stroke prediction system, performance optimization through the use of ensemble machine learning algorithms, performance assessment, and real-time model deployment through the use of Python Django are among the goals of the research. The study's potential to improve public health by lessening the severity and consequences of strokes through early diagnosis and treatment makes it significant. Data collection, preprocessing, model selection, evaluation, and real-time deployment using Python Django are all part of the research technique. Our dataset consists of 5110 rows of tuples and columns with total size of 69kg. The performance of our stroke prediction algorithm was evaluated using confusion metrics-consisting of accuracy, precision, recall and F1-score. At the end of the research, Random Forest model gave an accuracy of 98.5% compared to the existing model logistic regression which has 86% accuracy.

Prediction of machining performances in powder mixed electro-discharge machining to process skd61 steel by response surface methodology

In electro-discharge machining (EDM) with mixing powder, it is called powder mixed electro-discharge machining (PMEDM), then machining performances- i.e. material removal rate(MRR) and tool wear rate (TWR) has great significance in evaluating the effectiveness and machining accuracy of the machining method. Therefore, in this study, response surface methodology (RSM) was utilized for estimating functions of process variables {comprising peak current (Ip), pulse on time (Ton), and powder concentration (Cp)} for the machining performances for processing SKD61 steel during EDM process with tungsten compound powder. Box-Behnken matrix was utilized for designing and conducting a series of empirical trials. Analysis of variance (ANOVA) was applied to evaluate the adequate of predictive models. The outcomes reveal that the predicted models of MRR and TWR have a high precision with R2 values of MRR and TWR being 99.2% and 99.11%, respectively. The error comparison of the predictive and empirical values for the confirmed experiments is less than 5%, this once again consolidates that the developed models' accuracy. These development models can efficiently prognosticate the desired machining performances of the PMEDM method for processing SKD61 steel

Packaging machine vibration reduction by dynamic balancing

In this article vibrations transmitted to the frame of a packaging machine are reduced through dynamic balancing. It is known that unbalanced inertial forces and moments result in undesirable vibrations that negatively affect the performance and durability of machines. These shaking forces and shaking moments must be completely balanced to eliminate the vibrations. Balancing generally increases other dynamic characteristics like driving torque, bearing reactions in joints and the overall mass of the mechanism and can lead to a more complex mechanism. Instead of a complete balance of shaking force and moment, these can be minimized through optimization techniques. In this work, an optimization procedure is formulated to determine the masses and locations of counterweights that provides the minimum shaking force and moment of a packaging machine sealing head, thus reducing the vibrations transferred to the frame.

Determination of Ergonomic Factors of the Backpack Blowers Used in the Windrow of Hazelnuts

Ergonomics plays an important role in the design and use of agricultural machinery to protect the health and safety of workers. Lack of ergonomic design negatively affects worker discomfort and safety. Therefore, ergonomic design should ensure that workers can work comfortably, maintain correct posture, and minimize the risk of injury. Especially workers using backpack machines are exposed to physical fatigue, posture problems, risk of injury, and ergonomic effects due to vibration and noise. Considering all these, this study was conducted to determine the ergonomic factors (ergonomic analysis of the operator's working posture, operator's fatigue values, noise level, and dust concentration) that the operator is exposed to as a result of different body positions and moving the air diverter hose while using the backpack type blowers used to windrow the kernel+husked nuts falling on the orchard ground during the hazelnut harvest period. According to this, in all three ergonomic risk methods, the operator's body posture was found to be risky, and ergonomic adjustments were needed. Again, the operator's fatigue value, noise level, and dust concentration were obtained as 10.43 kcal min-1, 91.70 dB(A)-106.20 dB(A) (average 98.95 dB(A)), 19.241-21.390 mg m-3-air ( average 20.315 mg m-3-air), respectively. The identification of ergonomic factors is also very important to improve the user experience, prevent occupational accidents, and improve machine performance in general. With the identification of these factors, optimized solutions for the safety and comfort of users will be put forward by adopting a human-centered approach in machine design.

High-speed tooth-coil permanent magnet synchronous machine for motorized spindle application

The slender shape of the driving machine leads to a low rigidity and large axial thermal elongation of the motorized spindle, which deteriorates the machining precision. To solve these problems and pursue a more compact size, this paper investigates the feasibility of using a tooth-coil permanent magnet synchronous machine in a high-speed spindle, replacing the original motor that has the conventional distributed winding. Comprehensive performance and behavior of machines with distributed and tooth-coil windings are comparatively analyzed, in terms of the essential torque ripples, winding inductances, electromagnetic losses, rotor integrity, and heat dissipation of the spindle. Thorough numerical simulation results indicate that the newly designed tooth-coil winding solution shows significant advantages over the original design, regarding high rotor rigidity, low torque ripples, reduced electromagnetic losses, and reduced shaft thermal elongation. Prototypes and test setups for the high-speed tooth-coil machine are built, where preliminary measurements are carried out to validate the analysis results and system design.

Investigating Carded Yarn Quality through Cross-Doubling in the Draw frame: A Comprehensive Analysis

A carding machine's performance has an impact on the quality of the carded sliver, which in turn affects the quality of the carded yarn produced. Several factors can influence a machine's efficiency, resulting in fluctuations in the slivers generated over time. To achieve consistent and reproducible quality levels, slivers from all carding machines must be blended homogeneously. This blending process is vital for achieving homogeneity in the final product and maintaining a high quality standard. This can be achieved by cross-doubling. In this technique, carded slivers are arranged into categories of good, medium and low quality based on the nep removal efficiency of the carding machine behind the breaker draw frame. This is a specific type of doubling process. The focus of this research was the effectiveness of the aforementioned practice. Three carding machines were selected out of seven based on the quality level of the produced carded sliver, which was measured by nep removal efficiency. Yarn samples of 29.5 tex were produced from the slivers of the individual carding machines and by cross-doubling them at the breaker draw frame. Samples were collected at each stage of processing and tested. The results showed that cross-doubling significantly reduced variation in the imperfection level and yarn strength, but had very little effect on the mass variation level of the strands. Furthermore, the categorization of the four samples for selection was carried out using the Analytic Hierarchy Process method. This study will provide a guideline for new spinners to enhance yarn quality through cross-doubling on a draw frame machine.

Optimization of an IPMSM for Constant-Angle Square-Wave Control of a BLDC Drive

Interior permanent magnet synchronous machines (IPMSMs) driven with a square-wave control (i.e., six-step, block, or 120° control), known commonly as brushless direct current (BLDC) drives, are used widely due to their high power density and control simplicity. The advance firing (AF) angle is employed to achieve improved operation characteristics of the drive. The AF angle is, in general, applied to compensate for the commutation effects. In the case of an IPMSM, the AF angle can also be adjusted to exploit reluctance torque. In this paper, a detailed study was performed to understand its effect on the drive’s performance in regard to reluctance torque. Furthermore, a multi-objective optimization of the machine’s cross-section using neural network models was conducted to enhance performance at a constant AF angle. The reference and improved machine designs were evaluated in a system-level simulation, where the impact was considered of the commutation of currents. A significant improvement in the machine performance was achieved after optimizing the geometry and implementing a fixed AF angle of 10°.

Ultra‐fast finite element analysis of coreless axial flux permanent magnet synchronous machines

AbstractLarge‐scale design optimisation techniques enable the design of high‐performance electric machines. Electromagnetic 3D finite element analysis (FEA) is typically employed in optimisation studies for accurate analysis of axial flux permanent magnet (AFPM) machines, which require extensive computational resources. To reduce the computational burden, a FEA‐based mathematical method relying on the geometric and magnetic symmetry of coreless AFPM machines is proposed to estimate the machine performance indicators using the least number of FEA solutions, thereby significantly lowering the running time. This method is generally applicable to AFPM machines with low saturation effects and cogging torque as exemplified for a printed circuit board (PCB) stator coreless AFPM machine. To further reduce the computation time, a systematically simplified equivalent 3D FEA model for planar PCB coils integrated with this machine is also proposed. The practical implementation of the introduced method is elaborated based on an example optimisation study, and an analytical method for fast design scaling is also discussed. The results of the proposed approach are compared with detailed transient FEA results, and a prototype 26‐pole PCB stator coreless AFPM machine was also used to validate the results experimentally.

DESIGN OF COCONUT DEHUSKING MACHINE

The global coconut industry flourishes, generating food, beverages, and industrial products. However, traditional manual dehusking methods pose significant challenges, including being labor-intensive, time-consuming, and exposing workers to potential injuries. This research paper delves into the design and development of a pneumatic coconut dehusking machine incorporating a timer and sequencing module controlled by a microcontroller. The paper comprehensively explores the various components, their functionalities, the control system architecture, and potential areas for future advancements. It delves deeper into design considerations for optimizing machine performance, safety, and user experience. Keywords: Pneumatic controlled coconut dehusking, Microcontroller, Timer & Sequencing module, Automation

An iterated greedy algorithm with acceleration of job allocation probability for distributed heterogeneous permutation flowshop scheduling problem

Distributed manufacturing paradigm is becoming one of the dominant manufacturing models today. Heterogeneities between factories exist in fact due to the differences in process flexibility and machine performance. Most research focuses on identical distributed factories and overlooks the influence of heterogeneous factories on the subproblem of job allocation. This paper investigates a distributed heterogeneous permutation flowshop scheduling problem (DHPFSP) to minimize the makespan, and a mixed-integer linear programming (MILP) model is established. Building upon a special phenomenon of job assignment to a specific heterogeneous factory in DHPFSP, an iterated greedy algorithm with acceleration of job allocation probability (IGP) is proposed. To utilize this phenomenon, a job allocation probability matrix is introduced to describe the trend of job allocation, and a fast pass strategy with job allocation probability is suggested to speed up the algorithm search process. Furthermore, to generate a high-quality initial solution quickly for IGP, an NEH-based heuristic framework for distributed heterogeneous factory environment (NEHDHF) is proposed. In NEHDHF, several distinct initial job sequence generation strategies and a new first-f job allocation strategy are proposed for obtain a better initial solution. In computational experiments, there are 720 test instances designed and publicized. The IGP achieves 535 best solutions out of 720 instances. Statistically sound results demonstrate the effectiveness of the presented algorithms for the considered problem.

Study on the screening performance and parameter optimization of linear vibrating screen under the influence of sieve plate airflow

Screening is an important step in the preparation of machine made sand, and the screening performance of the screening machine is the key to improving the production efficiency and quality of machine made sand. This article first explores the influence of airflow generated by sieve plate vibration on particle motion on the sieve through numerical simulation, and verifies the reliability of the simulation model through experimental prototypes. Then, based on the CFD-DEM coupling model, the relationship between screening parameters and screening performance was studied. Finally, based on the screening results and the BP neural network optimized by the sparrow search algorithm, an evaluation model for screening parameters and screening performance was established, and a multi-objective genetic algorithm was used to optimize the high-performance screening parameter combination scheme. The comprehensive optimal performance parameters were obtained: vibration frequency of 15.5885 Hz, amplitude of 2.3789 mm, vibration direction angle of 50.5227, sieve obliquity of 16.6676, and feed rate of 20921 pieces/s.

Solar adsorption cooling system operating by activated–carbon–ethanol bed

One efficient way to convert small thermally energized into effective cooling is through adsorption cooling technology, which increases energy efficiency and reduces environmental pollution. This study's primary goal is to hypothetically examine the thermal coefficient of performing the solar adsorptive refrigerator machine operated with an activating carbon/Ethanol operating dual. The impact of different operating situations and design factors on the machine's performance is inspected and evaluated. The present double-bed solar energy adsorptive-cooler unit is modeled by thermodynamic methodology. Then, it was analyzed to evaluate its effectiveness work under Baghdad climate conditions. For the current study, the two-bed solar adsorption cooling unit with 0.5 kW capacity input heat 11893 that operates at 5 °C for the evaporator and 45 °C for the condenser is presented. The Engineering-Equation-Solver (EES) simulation program was created and used to solve the modeling equations that predict the optimal cycle performance and evaluate the optimum reasonable values of the operation parameters of the proposed system. The pressure range for the refrigeration cycle is 2.408 kPa for the evaporation state and 23.14 kPa for the condensation state. The findings demonstrate that an optimum coefficient of performance (COP) is 0.702 at 95 °C, a 20% performance increase, which generates 39.4 of cooling water. It produced 1 kg of chilled water for 2.463 kg of activated carbon at a temperature of 5°C. The improved solar-powered adsorption systems and refrigeration technologies are appealing substitutes that can satisfy energy demands in addition to meeting needs for cooling, ice production, air conditioning, and refrigeration preservation and safeguarding of the environment with Iraq's climate conditions.

Torque Capacity Improvement of Flux-Switching PM Machines Based on Directional Stator Permeance Design

As one type of flux modulation machines, flux-switching permanent magnet (FSPM) machines present high sensitivity to airgap structures. Therefore, both stator/rotor teeth and slot/pole combinations have significant influences on machine performance. However, the relationships between the optimal stator structure and maximum torque capability of the FSPM machine are barely investigated. Therefore, this paper is devoted to proposing a directional stator permeance design approach to achieve the maximum torque of the FSPM machines under a given rotor, and reveal the corresponding stator structure. First, the relations between torque and air-gap permeance are presented based on a constructed torque contribution equation, where amplitudes and phase angles of the stator permeance harmonics are determined. Then, main permeance harmonics are directionally optimized to enlarge positive torque, while negative contributions are inversed to be positive. Especially, two FSPMs with 6-slot/19-pole and 6-slot/13-pole are chosen as design examples, and their optimal design processes and torque performances have been deeply analyzed, which verifies the effectiveness of the proposed design approach.

Tuned Windings: the window of opportunity for the implementation of solid conductors in high frequency cryogenic electric machines

Optimization techniques can significantly improve the performance of electrical machines. The analysis and the optimization algorithms focus on computational efficiency. In this paper, the optimization of a high frequency electrical machine in cryogenic conditions is proposed. The losses introduced by AC current in a conductor are directly proportional with the applied frequency in terms of skin effect and proximity effect. The stator coil, made from two aluminium (Al) turns, in the presence of cryogenic coolants has been analysed at frequencies up to 1000 Hz. In order to reduce the AC losses introduced by the magnetic fields, Nonlinear Conjugate Gradient (NCG) method has been applied for the stator coil thickness optimization. Frequency dependence is observed in most simulations. In the presence of Liquid Hydrogen (LH2) coolant, Al 1100 conductor presents the minimum power loss.